Triple
T3754871
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Kulitan script |
E82020
|
entity |
| Predicate | scriptFeature |
P51137
|
FINISHED |
| Object | consonant-vowel syllabic characters |
—
|
LITERAL FINISHED |
How this triple was built (2 steps)
Every LLM step that produced this triple, in pipeline order — named-entity classification, the disambiguation choices (the exact options shown, with the pick highlighted), and the generated description. The batch + timestamp of each is in the Provenance table below.
NER
Named-entity recognition
gpt-5-mini
Instruction
Given a phrase, classify it is english named entity (e.g., persons, organizations, works of art) in Latin script, or not (e.g., literals, dates, URLs, verbose phrases). For disambiguation, the statement where the phrase occurs as object is also given. Please return a JSON object with `phrase` (string, the phrase being analyzed) and `is_ne` (boolean, indicating whether the phrase is a Named Entity).
Input
Phrase: consonant-vowel syllabic characters | Statement: [Kulitan script, scriptFeature, consonant-vowel syllabic characters]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: scriptFeature Context triple: [Kulitan script, scriptFeature, consonant-vowel syllabic characters]
-
A.
script
Indicates that an entity is associated with a written text or code (such as a screenplay, program, or written instructions) that defines its content or behavior.
-
B.
scriptOnFlag
Indicates that a script is attached to and/or executed when a specific flag or condition is set.
-
C.
scriptType
Indicates the classification or category of a script, specifying what kind of script it is (e.g., its format, purpose, or scripting language type).
-
D.
scriptCategory
Indicates the classification or type of script to which an entity (such as a written work, code, or performance text) belongs.
-
E.
scriptDirection
Indicates the direction in which a writing system or script is read or written (e.g., left-to-right, right-to-left, top-to-bottom).
- F. None of above. chosen
Provenance (4 batches)
The batch behind each pipeline step, in order, with when it ran. Timestamps are batch-level — stages were processed in waves, so the object chain (NER → NED1 → NEDg → NED2) reads in order, but predicate / elicitation batches can sit in a different wave.
| Step | Stage | Batch ID | Status | When |
|---|---|---|---|---|
| creating | Elicitation | batch_69ad8b1db40081908b61ffa6b78afd4d |
completed | March 8, 2026, 2:43 p.m. |
| NER | Named-entity recognition | batch_69adcb94ffc08190a7fd1ce71a15f787 |
completed | March 8, 2026, 7:18 p.m. |
| PD | Predicate disambiguation | batch_69adc04adebc819088d7f36d0ac343a6 |
completed | March 8, 2026, 6:30 p.m. |
| PDg | Predicate description generation | batch_69adc1560c248190b07438d766880990 |
completed | March 8, 2026, 6:35 p.m. |
Created at: March 8, 2026, 3:35 p.m.